• Strategies on reducing VGPR usage - and, where do they come from?

    Aside from a detrimental memory latency issue I reported in this thread, I also noticed that my OpenCL code on AMD GPUs suffered from large VGPR usage.   For the voxel-based Monte Carlo simulator, MCXCL (https:/...
    FangQ
    last modified by FangQ
  • OpenCL driver bug

    EDIT: reformat  EDIT 2: correct driver version   Found a weird behavior in AMD's OpenCL compiler. Code taken straight from Boost library:   __kernel void serial_adjacent_find(const uint size, __global...
    rosenrodt
    last modified by rosenrodt
  • OpenCL development for Radeon VII under Windows 7

    Hello!   Recently I've bought a Radeon VII for OpenCL development purposes.   I installed it in my dual-boot Windows 7 & Linux machine, and now I'm trying to setup a development environment.   My...
    be_dos
    last modified by be_dos
  • Looking for Linux/Open CL2.0 Driver for AMD A10-9620P

    Does AMD have any kind of official support ?   Some how, I can not for the life of me find a working OpenCL ( I would like OpenCL 2.0 ) for Linux and my computer. Surely there is ? The question is where ?  ...
    scarfez
    last modified by scarfez
  • host-device latencies?

    Doing recently some benchmarks and wonder if my host-device latencies are bound to my older hardware or are similar on newer systems?   OS: Ubuntu 18.04 x86-64 Device: AMD Radeon HD 7750   OpenCL gpu kerne...
    smato2018
    last modified by smato2018
  • Current status of OpenCL for a SI (R7 370) in Linux

    Hi,   As I asked in Linux OpenCL not working AMDGPU-PRO (max global size 0, CL_OUT_OF_HOST_MEMORY), the problem persist.   I tried both in Arch and in Ubuntu 18.04. If I go for mesa + amdgpu open source dr...
    userxx
    last modified by userxx
  • where to find AMD APP SDK 3.0 for Linux(no-X86/X86_X64 architecture)?

    Platform Information Firstly I‘ll post my platform info: arch-info    3.10.84-20.fc21.loongson.3.mips64el cpu-info  [loongson@localhost ~]$ lscpu Architecture: mips64 Byte Order: Litt...
    王石磊
    last modified by 王石磊
  • OPENCL user guide for Radeon VII

    Hello,   Is the opencl programmer's guide going to be updated to include programming  info and tips for the radeon vii? --
    dns.on.gpu
    last modified by dns.on.gpu
  • Is there a performance difference between HIP and OpenCL

    Is there any performance loss on AMD gpus if I program something in hip instead of Open CL ?   Are any of the other languages more or less performant ?
    jungle
    last modified by jungle
  • Error code -2 (Device not availaible) when running clCreateContextFromType

    Hello Everyone,   I'm currently retesting some OpenCL code and I recently had a problem on my code. When I'm trying to get the device list on my computer with the C++ Wrapper function ... I get a error...
    fyfy
    last modified by fyfy
  • OpenCL: Delay in inter-kernel execution when requesting callbacks

    Hi I have a problem with delays in kernel execution when I request callbacks from OpenCL. In my application, I need to execute kernels at a "very" high rate (around 300Hz), and I need a callback to my host applicati...
    nfogh
    last modified by nfogh
  • OpenCL: repeat kernel execution?

    I'm queuing kernels that modify a buffer over and over again and am wondering if there's a more efficient way to do what I'm doing.   Here's pseudocode:   for (int q = 0; q < iterations; q++) {  ...
    ivanisavich
    last modified by ivanisavich
  • Wavefront and kernel occupancy

    I reduced number or vgpr from 88 to 84. The number of wavefront per compute unit increased from 8 to 12. However, I cannot see any performance gain. The vgpr reduce should not slow down the performance of each work it...
    fancyix
    last modified by fancyix
  • SPIR for vega?

    Hi,   As seen here https://community.amd.com/message/2878648#2878652 or here https://community.amd.com/message/2846525#comment-2846525   Vega series doesn't seems to support SPIR or SPIR-V. However I can ...
    charlie.l
    last modified by charlie.l
  • S_WAKEUP instruction

    The Vega Shader ISA doc (https://developer.amd.com/wp-content/resources/Vega_Shader_ISA_28July2017.pdf) describes S_WAKEUP instruction as follows (I quote) -   Allow a wave to 'ping' all the other waves in its t...
    sp314
    last modified by sp314
  • Programming AMD GPUs with OpenACC

    Hi, I posted this same question here https://community.amd.com/message/2892646#comment-2892646 and I've been suggested to try ask the question in the OpenCL forum. It is mentioned in the HPC section (Accelerators for ...
    agabbana
    last modified by agabbana
  • Learning OpenCL: sha256, others

    Hi everyone,   I'm learning OpenCL and I'm making some slow and steady progress, but I'm not sure I'm understanding enqueueNDRangeKernel and workgroups and their size.  I think it has something to do with c...
    jyoungaus
    last modified by jyoungaus
  • How to pass a pointer to structure that contains a value in opencl

    I am trying to work on this code but everytime I gets runtime error "error: field may not be qualified with an address space global uint64_t external; Here is my data structure in hdr.h: typedef unsigned long uint64...
    avinashkrc
    last modified by avinashkrc
  • The values returned by clGetDeviceInfo() and clGetPlatformInfo() seem to be just a little off. Why?

    I've got Ubuntu Linux 16.04 with ROCm and AMDGPU-PRO drivers, and an R290x card, which is the only GPU I have on this computer. When I query the device name with clGetDeviceInfo(...CL_DEVICE_NAME...), for some reason,...
    sp314
    last modified by sp314
  • Why my VGPRs Usage increases so fast when I use this assignment statement code in OpenCL?

    if (condition) {*foundFlag = 1; dst[gid] = gid * crack_cnt + num; break; } This code is used in ending kernel funtion when password is found(2 AMD 7970 devices and OpenCL platform). *foundFlag is a pointer to a char v...
    yanmin950122
    last modified by yanmin950122